agent-eval

Compares coding AI agents side-by-side to measure which one works best for your tasks.

Installation
Run `npx skills add "https://github.com/affaan-m/ecc" --skill "agent-eval"` to install this skill, then follow its SKILL.md instructions for my next request.

Paste this into Claude Code, Cursor, or any agent that can run commands.

What this skill does
What it does: - Compares different AI coding assistants like Claude Code and Aider side by side - Runs the same tasks on each assistant and measures how many pass - Tracks cost, time, and how consistent results are across multiple tries - Creates reports showing which assistant works best for your needs When to use it: - When deciding which AI coding assistant to use for your team - When a new version of an AI tool comes out and you want to check if it still works well - When you want real data to prove which assistant is better instead of just guessing - Before switching to a new AI coding tool

The full skill text could not be loaded right now. It installs fine with the command above, or read it at the source.

Mirrored from the author's public source. Install counts from the open skills registry.

The systems behind these skills get built for partners every week.

Partner with us